dongarandClaude Opus 5.5
6ae2375194
nisse-dev now runs only the conversational loop. The gated state machine it was built alongside is gone: - Removed control.py, planner.py, executor.py, approvals.py, gates.py (command_form moves to loop/reader.py), publish.py and poller.py, the old assembly in agent.py (its shared helpers move to loop/build.py), the store's state-machine view (get_state, transition), their tests, the old end-to-end and live planning/milestone/gate tests, and specs/orchestrator.qnt with its scenarios. - Roles are driver, helper, expert and classifier; driver is required. loop:, roles.planner, roles.executor and tuning.executor are refused with what to use instead; tuning.driver takes the turn cap and failure limit. - The benchmark and the capability matrix measure the driver: the loop's own system prompt and tools, the task's plan as the agreed restatement. Task plans end with finish_milestone, so earlier runs show as (old); stored runs' executor tuning reads as the driver's. - A delegation on the loop records what its helper's alias resolved to (L9), as the old path's did. - The dump shows a work item's revision and what it waits for. - Behaviour the old tests covered and the loop shares stays covered: driver runs that fail on a model call, stop mid-turn, reset the failure count; go-aheads ignoring case and punctuation; a request too big to fit is never sent; the assembly tests, now on build_loop_agent. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PPQ14L3LikyefCMFBqEbKE
108 lines
3.7 KiB
Python
108 lines
3.7 KiB
Python
"""Live Gitea round trip in a repository of the run's own: push a branch,
|
|
open a PR, comment, and prove the L8 reconciler reads external truth
|
|
correctly, and that protection holds against the agent (D4).
|
|
"""
|
|
|
|
import uuid
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from e2e_support import fresh_repo, operator_gitea
|
|
|
|
from nisse_dev.config import AgentConfig
|
|
from nisse_dev.execution import SSHHost
|
|
from nisse_dev.git import GitError, GitRepo, SSHKey
|
|
from nisse_dev.gitea import GiteaClient, pull_request_reconciler
|
|
from nisse_dev.loop.build import remote_url
|
|
from nisse_dev.state import Intent
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
def intent_for(branch: str) -> Intent:
|
|
return Intent(
|
|
id=1,
|
|
kind="open_pr",
|
|
payload={"branch": branch},
|
|
status="pending",
|
|
created_at="t",
|
|
resolved_at=None,
|
|
)
|
|
|
|
|
|
def test_push_open_pr_and_reconcile(
|
|
tmp_path: Path, live_config: AgentConfig, gitea: GiteaClient, ssh_host: SSHHost
|
|
) -> None:
|
|
client = gitea
|
|
with fresh_repo(
|
|
operator_gitea(live_config.gitea_url),
|
|
uuid.uuid4().hex[:8],
|
|
tmp_path / "keys",
|
|
agent=client.whoami(),
|
|
) as fresh:
|
|
_round_trip(
|
|
tmp_path, client, ssh_host, fresh.name, SSHKey(fresh.push_key.read_text())
|
|
)
|
|
|
|
|
|
def _round_trip(
|
|
tmp_path: Path, client: GiteaClient, ssh_host: SSHHost, repo_path: str, key: SSHKey
|
|
) -> None:
|
|
account = client.whoami()
|
|
assert "testing" in account, (
|
|
f"live tests must run as a testing account, not {account}"
|
|
)
|
|
|
|
branch = f"live-test-{uuid.uuid4().hex[:8]}"
|
|
reconcile = pull_request_reconciler(client, repo_path)
|
|
|
|
# Before the PR exists, external truth says the effect has not happened.
|
|
assert reconcile(intent_for(branch)) is False
|
|
|
|
# Pushed the way the agent does: from the build VM (here the throwaway
|
|
# sshd), with the repository's deploy key, never the API token.
|
|
url = remote_url(client, repo_path, key)
|
|
repo = GitRepo(ssh_host, tmp_path / "work", known_hosts=str(tmp_path / "kh"))
|
|
repo.init()
|
|
repo._git("fetch", "-q", url, "main", credential=key)
|
|
repo._git("checkout", "-q", "-B", "work", "FETCH_HEAD")
|
|
repo.configure_identity(account, f"{account}@example.test")
|
|
(repo.root / f"{branch}.txt").write_text("live test artifact\n")
|
|
assert repo.commit_all("Live test commit") is not None
|
|
|
|
pr = None
|
|
try:
|
|
repo.push(url, branch, credential=key)
|
|
pr = client.open_pull_request(
|
|
repo_path,
|
|
head=branch,
|
|
base="main",
|
|
title=f"live test {branch}",
|
|
body="Opened by the nisse-dev live test suite.",
|
|
)
|
|
assert pr.head == branch
|
|
|
|
client.post_comment(repo_path, pr.number, "live test comment")
|
|
bodies = [c.body for c in client.list_comments(repo_path, pr.number)]
|
|
assert "live test comment" in bodies
|
|
|
|
# Now the same reconciler must see the effect and refuse to repeat it.
|
|
assert reconcile(intent_for(branch)) is True
|
|
|
|
# D4 is only real if the server enforces it. The agent's own token
|
|
# must not be able to merge the PR it just opened, and its push credential
|
|
# must not be able to push to the protected default branch at all.
|
|
merged = client._http.post(
|
|
f"/repos/{repo_path}/pulls/{pr.number}/merge", json={"Do": "merge"}
|
|
)
|
|
assert merged.status_code >= 400, (
|
|
"the agent merged its own PR: branch protection is not enforcing "
|
|
"the human gate"
|
|
)
|
|
with pytest.raises(GitError):
|
|
repo.push(url, "main", credential=key)
|
|
finally:
|
|
if pr is not None:
|
|
client.close_pull_request(repo_path, pr.number)
|
|
client.close()
|